© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4357
    Prev
    Next
    INDEX
    Explanations

    pounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lèvres
    -0.84
     vérit
    -0.77
     oreilles
    -0.70
     genoux
    -0.68
     rayures
    -0.66
     thèmes
    -0.66
     varandra
    -0.65
     gouttes
    -0.65
     nuages
    -0.65
     larmes
    -0.63
    POSITIVE LOGITS
    ⓧ
    0.72
     tanks
    0.69
     operations
    0.68
     camps
    0.67
    UnsafeEnabled
    0.67
     partnerships
    0.65
     OFDb
    0.65
    UnitTesting
    0.64
     missions
    0.63
    NameInMap
    0.62
    Activations Density 0.000%

    No Known Activations